© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40221
    Prev
    Next
    INDEX
    Explanations

    throwing games and targets

    np_acts-logits-general · gemini-2.5-flash-lite

    team sports combining elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     film
    0.49
     cinema
    0.48
    URL
    0.46
     /
    0.44
    UUID
    0.44
     $.
    0.43
    $.
    0.42
    ACK
    0.42
     Nowadays
    0.42
    丁
    0.42
    POSITIVE LOGITS
    𝙥
    0.50
     sepanjang
    0.49
    слежи
    0.49
    ťaž
    0.47
    قی
    0.45
    ப்படுக
    0.45
    itatively
    0.44
    जैसा
    0.44
    insieme
    0.44
    镳
    0.43
    Activations Density 0.002%

    No Known Activations